| Name | Quant method | Size |
|---|---|---|
| OpenMistral-MoE.Q2_K.gguf | Q2_K | 8.24GB |
| OpenMistral-MoE.IQ3_XS.gguf | IQ3_XS | 9.21GB |
| OpenMistral-MoE.IQ3_S.gguf | IQ3_S | 9.73GB |
| OpenMistral-MoE.Q3_K_S.gguf | Q3_K_S | 9.72GB |
| OpenMistral-MoE.IQ3_M.gguf | IQ3_M | 2.0GB |
| OpenMistral-MoE.Q3_K.gguf | Q3_K | 10.79GB |
| OpenMistral-MoE.Q3_K_M.gguf | Q3_K_M | 10.79GB |
| OpenMistral-MoE.Q3_K_L.gguf | Q3_K_L | 11.68GB |
| OpenMistral-MoE.IQ4_XS.gguf | IQ4_XS | 12.15GB |
| OpenMistral-MoE.Q4_0.gguf | Q4_0 | 12.69GB |
| OpenMistral-MoE.IQ4_NL.gguf | IQ4_NL | 12.81GB |
| OpenMistral-MoE.Q4_K_S.gguf | Q4_K_S | 11.02GB |
| OpenMistral-MoE.Q4_K.gguf | Q4_K | 13.61GB |
| OpenMistral-MoE.Q4_K_M.gguf | Q4_K_M | 13.61GB |
| OpenMistral-MoE.Q4_1.gguf | Q4_1 | 14.09GB |
| OpenMistral-MoE.Q5_0.gguf | Q5_0 | 15.48GB |
| OpenMistral-MoE.Q5_K_S.gguf | Q5_K_S | 15.48GB |
| OpenMistral-MoE.Q5_K.gguf | Q5_K | 15.96GB |
| OpenMistral-MoE.Q5_K_M.gguf | Q5_K_M | 15.96GB |
| OpenMistral-MoE.Q5_1.gguf | Q5_1 | 16.88GB |
| OpenMistral-MoE.Q6_K.gguf | Q6_K | 18.46GB |
| OpenMistral-MoE.Q8_0.gguf | Q8_0 | 23.9GB |
1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Yash21/OpenMistral-MoE"
8
9tokenizer = AutoTokenizer.from_pretrained(model)
10pipeline = transformers.pipeline(
11 "text-generation",
12 model=model,
13 model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
14)
15
16messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
17prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
18outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
19print(outputs[0]["generated_text"])